Kimi K2 Base
Open-weight trillion-parameter mixture-of-experts base model with 32 billion active parameters.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 67.2
Strong open weights and broad download access create high deployment and control difficulty; the base checkpoint has less instruction following and autonomy than the instruction tier.
News tied to Kimi K2 Base
The model score of 67.2 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
Moonshot AI releases open-weight Kimi K2 base and instruction models
Moonshot AI published Kimi K2, a trillion-parameter mixture-of-experts family with 32 billion active parameters, open weights and an instruction model designed for tool use and agentic tasks.
- Full item contribution
- +0.19
- Kimi K2 Base equal share
- +0.10
Model score history
-
R3
Doom Score 67.2
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R2
Doom Score 67.5
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 68.3
New exact public model profile with authoritative repository creation timestamp.
12 Aug 2026